Hugging Face's logo

ytonthat
/
drbert-7gb-finedtuned-ner

Token Classification
Transformers
TensorBoard
Safetensors
camembert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
ytonthat commited on
Commit
36bf2d3
·
verified ·
1 Parent(s): c51d65c

Training in progress, epoch 1

Browse files
Files changed (9) hide show
  1. config.json +73 -0
  2. model.safetensors +3 -0
  3. runs/Mar01_02-18-45_1cc23fee8ba3/events.out.tfevents.1709259740.1cc23fee8ba3.4565.0 +3 -0
  4. runs/Mar01_02-38-39_1cc23fee8ba3/events.out.tfevents.1709260729.1cc23fee8ba3.4565.2 +3 -0
  5. sentencepiece.bpe.model +3 -0
  6. special_tokens_map.json +55 -0
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +76 -0
  9. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Dr-BERT/DrBERT-7GB",
3
+ "architectures": [
4
+ "CamembertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 5,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 6,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "O",
15
+ "1": "B-LIVB",
16
+ "2": "I-LIVB",
17
+ "3": "B-PROC",
18
+ "4": "I-PROC",
19
+ "5": "B-ANAT",
20
+ "6": "I-ANAT",
21
+ "7": "B-DEVI",
22
+ "8": "I-DEVI",
23
+ "9": "B-CHEM",
24
+ "10": "I-CHEM",
25
+ "11": "B-GEOG",
26
+ "12": "I-GEOG",
27
+ "13": "B-PHYS",
28
+ "14": "I-PHYS",
29
+ "15": "B-PHEN",
30
+ "16": "I-PHEN",
31
+ "17": "B-DISO",
32
+ "18": "I-DISO",
33
+ "19": "B-OBJC",
34
+ "20": "I-OBJC"
35
+ },
36
+ "initializer_range": 0.02,
37
+ "intermediate_size": 3072,
38
+ "label2id": {
39
+ "B-ANAT": 5,
40
+ "B-CHEM": 9,
41
+ "B-DEVI": 7,
42
+ "B-DISO": 17,
43
+ "B-GEOG": 11,
44
+ "B-LIVB": 1,
45
+ "B-OBJC": 19,
46
+ "B-PHEN": 15,
47
+ "B-PHYS": 13,
48
+ "B-PROC": 3,
49
+ "I-ANAT": 6,
50
+ "I-CHEM": 10,
51
+ "I-DEVI": 8,
52
+ "I-DISO": 18,
53
+ "I-GEOG": 12,
54
+ "I-LIVB": 2,
55
+ "I-OBJC": 20,
56
+ "I-PHEN": 16,
57
+ "I-PHYS": 14,
58
+ "I-PROC": 4,
59
+ "O": 0
60
+ },
61
+ "layer_norm_eps": 1e-12,
62
+ "max_position_embeddings": 514,
63
+ "model_type": "camembert",
64
+ "num_attention_heads": 12,
65
+ "num_hidden_layers": 12,
66
+ "pad_token_id": 1,
67
+ "position_embedding_type": "absolute",
68
+ "torch_dtype": "float32",
69
+ "transformers_version": "4.38.1",
70
+ "type_vocab_size": 1,
71
+ "use_cache": true,
72
+ "vocab_size": 32005
73
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1637e97f5d832e633df45864b2f164bd328d39110521ea52b6faef13227fd584
3
+ size 440213956
runs/Mar01_02-18-45_1cc23fee8ba3/events.out.tfevents.1709259740.1cc23fee8ba3.4565.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a421d552cdd606dcd92f3fbe3ade4b80cb727000051f2ef382790868ba2d609
3
+ size 7187
runs/Mar01_02-38-39_1cc23fee8ba3/events.out.tfevents.1709260729.1cc23fee8ba3.4565.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cd36365925af7dfd989736b32e47c1f5c6026469e7b32570a468a0f3110b763
3
+ size 5908
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:701a6bfe3db86b7bc1f4174e54f11bc24da195751c04a3ccea354a599de5c43b
3
+ size 791347
special_tokens_map.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<s>NOTUSED",
4
+ "</s>NOTUSED"
5
+ ],
6
+ "bos_token": {
7
+ "content": "<s>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "cls_token": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "eos_token": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "mask_token": {
28
+ "content": "<mask>",
29
+ "lstrip": true,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ },
34
+ "pad_token": {
35
+ "content": "<pad>",
36
+ "lstrip": false,
37
+ "normalized": false,
38
+ "rstrip": false,
39
+ "single_word": false
40
+ },
41
+ "sep_token": {
42
+ "content": "</s>",
43
+ "lstrip": false,
44
+ "normalized": false,
45
+ "rstrip": false,
46
+ "single_word": false
47
+ },
48
+ "unk_token": {
49
+ "content": "<unk>",
50
+ "lstrip": false,
51
+ "normalized": false,
52
+ "rstrip": false,
53
+ "single_word": false
54
+ }
55
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>NOTUSED",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>NOTUSED",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "5": {
36
+ "content": "<s>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "6": {
44
+ "content": "</s>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "32004": {
52
+ "content": "<mask>",
53
+ "lstrip": true,
54
+ "normalized": true,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ }
59
+ },
60
+ "additional_special_tokens": [
61
+ "<s>NOTUSED",
62
+ "</s>NOTUSED"
63
+ ],
64
+ "bos_token": "<s>",
65
+ "clean_up_tokenization_spaces": true,
66
+ "cls_token": "<s>",
67
+ "eos_token": "</s>",
68
+ "mask_token": "<mask>",
69
+ "max_len": 512,
70
+ "model_max_length": 512,
71
+ "pad_token": "<pad>",
72
+ "sep_token": "</s>",
73
+ "sp_model_kwargs": {},
74
+ "tokenizer_class": "CamembertTokenizer",
75
+ "unk_token": "<unk>"
76
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e356ae7123234e2208753cf49185186ef8c17b7f248d291e7af3e62212c6adc
3
+ size 4920